{"total":74,"rows":[{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149,"area":null},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128,"area":null},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2201.04850","title":"Bridging Video-text Retrieval with Multiple Choice Questions","created":"2022-01-13","cited_by_count":79,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2104.12671","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","created":"2021-04-26","cited_by_count":62,"area":null},{"id":"2112.00656","title":"Object-aware Video-language Pre-training for Retrieval","created":"2021-12-01","cited_by_count":57,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2204.07441","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","created":"2022-04-15","cited_by_count":33,"area":"mllm"},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2204.12408","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","created":"2022-04-26","cited_by_count":29,"area":null},{"id":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2112.01832","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","created":"2021-12-03","cited_by_count":23,"area":null},{"id":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","cited_by_count":20,"area":null},{"id":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20,"area":null},{"id":"2212.07086","title":"NLIP: Noise-robust Language-Image Pre-training","created":"2022-12-14","cited_by_count":20,"area":null},{"id":"2204.03382","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","created":"2022-04-07","cited_by_count":19,"area":null},{"id":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2301.12644","title":"Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2210.11929","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","created":"2022-10-21","cited_by_count":16,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2212.07892","title":"Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics","created":"2022-12-15","cited_by_count":14,"area":null},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2301.07463","title":"Temporal Perceiving Video-Language Pre-training","created":"2023-01-18","cited_by_count":12,"area":null},{"id":"2209.11388","title":"LGDN: Language-Guided Denoising Network for Video-Language Modeling","created":"2022-09-23","cited_by_count":11,"area":null},{"id":"2207.04858","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","created":"2022-07-11","cited_by_count":9,"area":null},{"id":"2212.11790","title":"Normalized Contrastive Learning for Text-Video Retrieval","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2301.01953","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2508.14015","title":"Backdooring Self-Supervised Contrastive Learning by Noisy Alignment","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2112.00775","title":"Routing with Self-Attention for Multimodal Capsule Networks","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2210.06881","title":"RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2303.03131","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2310.16822","title":"Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2111.14547","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2112.12182","title":"Fine-grained Multi-Modal Self-Supervised Learning","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2208.11553","title":"MuMUR : Multilingual Multimodal Universal Retrieval","created":"2022-08-24","cited_by_count":3,"area":"mllm"},{"id":"2406.06594","title":"Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2203.07720","title":"Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2405.07202","title":"Unified Video-Language Pre-training with Synchronized Audio","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2409.11059","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2212.07619","title":"Curriculum Learning Meets Weakly Supervised Modality Correlation Learning","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2310.19554","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2401.17773","title":"SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2311.17267","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2403.08224","title":"REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2407.11677","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","created":"2024-07-16","cited_by_count":0,"area":null}],"next_cursor":null}